ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present ResemBrick, a method to create buildable colored brick models of 3D objects from photos while balancing visual accuracy and physical stability. Unlike past approaches that fix the voxel grid early, their system chooses which voxels to fill based on a budget and resolution, optimizing appearance and buildability together. They ensure no loose or unstable bricks by combining smart placement and a repair step, leading to better-looking and sturdier models than previous methods. Their work shows it's important to handle discretizing shapes and assembling bricks as connected problems.
voxel grid3D reconstructiondiscretizationoccupancy completiongreedy placementstructural stabilityperceptual fidelitybrick modelingresolution-conditioned networkphysical assembly constraints
Authors
Xilun Chen, Hanwen Wan, Yusong Zhao, Zexin Lin, Ruixiang Liao, Xiaoqiang Ji
Abstract
Producing a hand-buildable, colored brick model of a 3D object from a few casual photographs is a clean testbed for a broader challenge: generating 3D content that meets hard physical-assembly constraints under a discrete, budget-limited voxel grid. On a coarse lattice, visual resemblance and structural stability pull against each other, yet prior brick pipelines address only one side and treat voxelization as fixed preprocessing rather than a variable to optimize. We present ResemBrick, which couples the two. Budgeted occupancy completion reframes discretization as allocation: given a target occupied-voxel count, a single resolution-conditioned network decides in one feed-forward pass which surface voxels to fill for best appearance, one weight set spanning 13 resolutions. Buildability by construction then combines support- and look-ahead-aware greedy placement with a deterministic, provably terminating repair that grounds every floating component. Under a matched budget, ResemBrick surpasses existing voxel selectors in perceptual fidelity while uniquely reaching zero floating and zero unstable bricks on unfiltered held-out objects; as a complete pipeline, it attains the best perceptual fidelity among prior brick-construction systems. Our results point to treating discretization and assembly as tightly coupled stages rather than independent ones.